Originally posted on LinkedIn on July 22, 2026.
In February, Block generously freed up 100% of my time. Since then, I’ve spent almost every waking hour building Nous Ergon, an applied AI lab.
I have three products in flight:
- Crucible — an experiment harness for testing agentic and financial strategies
- Metron — an agent-powered investment dashboard
- Vires — a strength-training app with an AI coach
I’ve also built mnemon, an open-source memory server for LLMs, which came out of a problem I kept hitting along the way: every LLM platform now ships with its own memory, but each one is a silo. Mnemon gives every LLM I run, across any client, one shared long-term memory.
“Nous Ergon” (pronounced NOOS AIR-gon) is Greek for “intelligence at work.” I’ve set up my workflow so agents handle most tasks while I focus on building. A backlog groomer routes every task to a model suited to its complexity and keeps my open PRs healthy. An LLM judge checks every agent in my research pipeline. Sensors watch system health, and I’m developing an “overseer” so that the system largely maintains itself.
I’ll go deeper on my setup, and on my products in development, in future posts.
Stay tuned!